OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
Implicit neural representation (INR) is a popular approach for arbitrary-scale image super-resolution (SR), as a key component of INR, position encoding improves its representation ability. Motivated by position encoding, we propose orthogonal position encoding (OPE) - an extension of position encoding - and an OPE-Upscale module to replace the INR-based upsampling module for arbitrary-scale image super-resolution. Same as INR, our OPE-Upscale Module takes 2D coordinates and latent code as inputs; however it does not require training parameters. This parameter-free feature allows the OPE-Upscale Module to directly perform linear combination operations to reconstruct an image in a continuous manner, achieving an arbitrary-scale image reconstruction. As a concise SR framework, our method has high computing efficiency and consumes less memory comparing to the state-of-the-art (SOTA), which has been confirmed by extensive experiments and evaluations. In addition, our method has comparable results with SOTA in arbitrary scale image super-resolution. Last but not the least, we show that OPE corresponds to a set of orthogonal basis, justifying our design principle.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionImage Super-ResolutionPositionSuper-ResolutionSimilar Papers 제목 키워드 기반
Multi-RIS Discrete-Phase Encoding for Interpath-Interference-Free Channel Estimation
Reconfigurable intelligent surfaces (RISs) are one of the foremost technological enablers of future wireless systems. They improve communication and localization by providing a strong non-line-of-sight path to the receiv…
OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation
We introduce a parameter-efficient adaptation method for panel-aware in-context image generation with pre-trained diffusion transformers. The key idea is to compose learnable, panel-specific orthogonal operators onto the…
Image GenerationGroup Orthogonal Low-Rank Adaptation for RGB-T Tracking
Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained parameters and fine-tuning only a small set of parameters. This set forms …
parameter-efficient fine-tuningRgb-T TrackingLinearized Relative Positional Encoding
Relative positional encoding is widely used in vanilla and linear transformers to represent positional information. However, existing encoding methods of a vanilla transformer are not always directly applicable to a line…
image-classificationImage ClassificationLanguage ModelingLanguage Modelling+2Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding
Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many curren…
Arithmetic ReasoningLanguage ModelingLanguage Modellingparameter-efficient fine-tuning+1